Enhanced Analysis and Remediation of Network Performance

1. A method for detecting and remediating network performance issues, the method comprising: receiving, at a network analytics machine learning model, network performance data comprising system log data and network configuration data; generating, by the network analytics machine learning model, using natural language processing, network performance metrics based on text of the system log data; determining, by the network analytics machine learning model, based on a comparison of the network performance metrics to training data input to the network analytics machine learning model, that the network performance metrics fail to satisfy a performance threshold; generating, by the network analytics machine learning model, an alert indicative of the network performance metrics failing to satisfy the performance threshold; identifying, by the network analytics machine learning model, a root cause of the network performance metrics failing to satisfy the performance threshold, the network performance metrics associated with a first network resource, and the root cause associated with a second network resource; selecting, by the network analytics machine learning model, a remediation action associated with modifying the second network resource; modifying, by the network analytics machine learning model, the second network resource based on the selection; generating, by the network analytics machine learning model, a use case associated with the network performance metrics, the use case comprising the root cause and the remediation action; and presenting, by the network analytics machine learning model, an indication that the remediation action was selected.

2. The method of claim 1, further comprising: receiving, at the network analytics machine learning model, second network performance data comprising system log data and second network configuration data; determining, by the network analytics machine learning model, that the network performance data satisfies one or more criteria; determining, by the network analytics machine learning model, that the second network performance data fails to satisfy one or more criteria; sending, by the network analytics machine learning model, the network performance data as data stream inputs to a natural language processing layer of the network analytics machine learning model based on the determination that the network performance data satisfies one or more criteria; and refraining from sending, by the network analytics machine learning model, the second network performance data as data stream inputs to the natural language processing layer of the network analytics machine learning model based on the determination that the second network performance data fails to satisfy the one or more criteria.

3. The method of claim 1, further comprising: receiving, at the network analytics machine learning model, second network performance data comprising system log data and second network configuration data; selecting, by the network analytics machine learning model, based on a comparison of the second network performance data to the use case, the use case as a response to the second network performance data; selecting, by the network analytics machine learning model, the remediation action based on the selection of the use case; and modifying, by the network analytics machine learning model, the second network resource based on the selection of the use case.

4. The method of claim 1, wherein the network performance data are received at an edge device of a network, the method further comprising: authenticating, by the network analytics machine learning model, a user; and identifying, by the edge device, based on the authentication, network resources from which to receive the network performance data, the network resources comprising the first network resource and the second network resource.

5. The method of claim 1, wherein the training data comprise the performance threshold, the method further comprising: modifying, by the network analytics machine learning model, the performance threshold; receiving, at the network analytics machine learning model, second network performance data comprising system log data and second network configuration data; and determining, by the network analytics machine learning model, based on a comparison of the second network performance data to the modified performance threshold, that the second network performance data satisfies the modified performance threshold.

6. The method of claim 1, further comprising: modifying, by the network analytics machine learning model, the use case, wherein the modification comprises at least one of modifying the root cause or the remediation action.

7. The method of claim 1, further comprising: receiving, at the network analytics machine learning model, second network performance data comprising system log data and second network configuration data; determining, by the network analytics machine learning model, that the second network performance data fails to satisfy the performance threshold; identifying, by the network analytics machine learning model, a correlation between the network performance metrics and the second network performance data failing to satisfy the performance threshold; and determining, by the network analytics machine learning model, based on the correlation, that the root cause is associated with the second network performance data.

8. A system for detecting and remediating network performance issues, the system comprising at least one processor coupled to memory, the at least one processor configured to: receive, using a messaging queue, network performance data comprising system log data and network configuration data; generate, using natural language processing, network performance metrics based on text of the system log data; determine, using a machine learning model, based on a comparison of the network performance metrics to training data input to the machine learning model, that the network performance metrics fail to satisfy a performance threshold; generate, using the machine learning model, an alert indicative of the network performance metrics failing to satisfy the performance threshold; identify, using the machine learning model, a root cause of the network performance metrics failing to satisfy the performance threshold, the network performance metrics associated with a first network resource, and the root cause associated with a second network resource; select, using the machine learning model, a remediation action associated with modifying the second network resource; modify the second network resource based on the selection; generate a use case associated with the network performance metrics, the use case comprising the root cause and the remediation action; and present an indication that the remediation action was selected.

9. The system of claim 8, wherein the at least one processor is further configured to: receive, using the messaging queue, second network performance data comprising system log data and second network configuration data; determine, using the machine learning model, that the network performance data satisfies one or more criteria; determine, using the machine learning model, that the second network performance data fails to satisfy one or more criteria; send the network performance data as data stream inputs to a natural language processing layer of the machine learning model based on the determination that the network performance data satisfies one or more criteria; and refrain from sending the second network performance data as data stream inputs to the natural language processing layer of the machine learning model based on the determination that the second network performance data fails to satisfy the one or more criteria.

10. The system of claim 8, wherein the at least one processor is further configured to: receive, using the messaging queue, second network performance data comprising system log data and second network configuration data; select, using the machine learning model, based on a comparison of the second network performance data to the use case, the use case as a response to the second network performance data; select, using the machine learning model, the remediation action based on the selection of the use case; and modify, using the machine learning model, the second network resource based on the selection of the use case.

11. The system of claim 8, wherein the network performance data are received at an edge device of a network, wherein the at least one processor is further configured to: authenticate a user; and identify, based on the authentication, network resources from which to receive the network performance data, the network resources comprising the first network resource and the second network resource.

12. The system of claim 8, wherein the training data comprise the performance threshold, and wherein the at least one processor is further configured to: modify, using the machine learning model, the performance threshold; receive, using the messaging queue, second network performance data comprising system log data and second network configuration data; and determine, using the machine learning model, based on a comparison of the second network performance data to the modified performance threshold, that the second network performance data satisfies the modified performance threshold.

13. The system of claim 8, wherein the at least one processor is further configured to: modify, using the machine learning model, the use case, wherein the modification comprises at least one of modifying the root cause or the remediation action.

14. The system of claim 8, wherein the at least one processor is further configured to: receive, using the messaging queue, second network performance data comprising system log data and second network configuration data; determine, using the machine learning model, that the second network performance data fails to satisfy the performance threshold; identify, using the machine learning model, a correlation between the network performance metrics and the second network performance data failing to satisfy the performance threshold; and determine, using the machine learning model, based on the correlation, that the root cause is associated with the second network performance data.